README.md
Chroma is an open-source embedding database: store, index and query vectors for retrieval-augmented generation, with a simple Python API.
pip install chromadb
Explore / Chroma
chroma-core
Chroma
Open-source embedding database for building AI apps with retrieval.
29,097 2,452 Python Apache-2.0updated yesterday
Continue your stack
What teams reach for next — and why each earns a place beside Chroma. Ranked by curator confidence.
Pairs well with
xberg
Rust-core document-intelligence engine with 15 language bindings: turns 96 formats — PDF, Office, images, audio, code — into clean text, tables and RAG-ready chunks. Library, CLI, REST or MCP.
Why it fitsNatural RAG pairing: Xberg does the front half (parse → clean text → syntax-aware chunks → local or hosted embeddings) and Chroma stores and retrieves those vectors. Xberg feeds the index; Chroma serves the queries.
chunkr
Document intelligence API in Rust: layout analysis, OCR with bounding boxes, and semantic chunking that turn PDFs, PPTs and Word docs into RAG-ready structured chunks.
Why it fitsAdjacent RAG pipeline stages: chunkr turns PDFs into RAG-ready semantic chunks; Chroma is the embedding store those chunks land in for retrieval.
olmocr
Open toolkit that linearizes messy PDFs — scans, tables, equations, handwriting — into clean ordered Markdown with a self-hosted vision-language model. Built for LLM training data and RAG ingestion.
Why it fitsolmocr's cleaned text is exactly what you embed and store for retrieval — feed its output into Chroma as the vector store behind a RAG app. Looser than the LlamaIndex pairing since any embedder/DB works, but Chroma is the natural open-source landing spot.
Alternative to See all + compare →
zvec
Alibaba's open-source in-process vector database: billion-scale similarity search embedded in your app, with DiskANN on-disk indexing, native full-text search and hybrid retrieval.
Why it fitsSame job — the embedding store under a RAG pipeline. Chroma is the Python-native developer default; Zvec is the in-process C++ engine betting on raw speed, DiskANN memory economics and built-in hybrid retrieval.
omnigraph
Lakehouse graph database for agent context — graph, vector and full-text retrieval fused in one runtime on branchable Lance/S3 storage; agent fleets write on isolated branches and merge Git-style.
Why it fitsSame slot in the stack — the store your AI app's retrieval hits — opposite ends of the spectrum: Chroma is a lightweight embedding DB you outgrow; omnigraph fuses graph traversal, ANN and full-text with versioned branching, at the cost of running a declared-as-code server.
MemMachine
Long-term memory layer for AI agents — episodic (graph), profile (SQL) and working memory behind Python/TS SDKs, REST and MCP; ships LangChain, LangGraph, CrewAI and LlamaIndex integrations.
Why it fitsSame slot — 'what my agent remembers' — different bets: Chroma is a general embedding store you shape into memory; MemMachine is purpose-built memory with episodic/profile/working tiers, at the cost of running Neo4j + SQL.